Search

BACKGROUND A number of studies have shown promising performance of artificial intelligence (AI) algorithms for diagnosis of lesions in skin cancer. To date, none of these have assessed algorithm performance in the real-world setting. OBJECTIVE The aim of this project is to evaluate practical issues of implementing a convolutional neural network developed by MoleMap Ltd and Monash University eResearch in the clinical setting. METHODS Participants were recruited from the Alfred Hospital and Skin Health Institute, Melbourne, Australia, from November 1, 2019, to May 30, 2021. Any skin lesions of concern and at least two additional lesions were imaged using a proprietary dermoscopic camera. Images were uploaded directly to the study database by the research nurse via a custom interface installed on a clinic laptop. Doctors recorded their diagnosis and management plan for each lesion in real time. A pre-post study design was used. In the preintervention period, participating doctors were blinded to AI lesion assessment. An interim safety analysis for AI accuracy was then performed. In the postintervention period, the AI algorithm classified lesions as benign, malignant, or uncertain after the doctors’ initial assessment had been made. Doctors then had the opportunity to record an updated diagnosis and management plan. After discussing the AI diagnosis with the patient, a final management plan was agreed upon. RESULTS Participants at both sites were high risk (for example, having a history of melanoma or being transplant recipients). 743 lesions were imaged in 214 participants. In total, 28 dermatology trainees and 17 consultant dermatologists provided diagnoses and management decisions, and 3 experienced teledermatologists provided remote assessments. A dedicated research nurse was essential to oversee study processes, maintain study documents, and assist with clinical workflow. In cases where AI algorithm and consultant dermatologist diagnoses were discordant, participant anxiety was an important factor in the final agreed management plan to biopsy or not. CONCLUSIONS Although AI algorithms are likely to be of most use in the primary care setting, higher event rates in specialist settings are important for the initial assessment of algorithm safety and accuracy. This study highlighted the importance of considering workflow issues and doctor-patient-AI interactions prior to larger-scale trials in community-based practices. CLINICALTRIAL ClinicalTrials.gov NCT04040114; https://clinicaltrials.gov/ct2/show/NCT04040114

Background A number of studies have shown promising performance of artificial intelligence (AI) algorithms for diagnosis of lesions in skin cancer. To date, none of these have assessed algorithm performance in the real-world setting. Objective The aim of this project is to evaluate practical issues of implementing a convolutional neural network developed by MoleMap Ltd and Monash University eResearch in the clinical setting. Methods Participants were recruited from the Alfred Hospital and Skin Health Institute, Melbourne, Australia, from November 1, 2019, to May 30, 2021. Any skin lesions of concern and at least two additional lesions were imaged using a proprietary dermoscopic camera. Images were uploaded directly to the study database by the research nurse via a custom interface installed on a clinic laptop. Doctors recorded their diagnosis and management plan for each lesion in real time. A pre-post study design was used. In the preintervention period, participating doctors were blinded to AI lesion assessment. An interim safety analysis for AI accuracy was then performed. In the postintervention period, the AI algorithm classified lesions as benign, malignant, or uncertain after the doctors’ initial assessment had been made. Doctors then had the opportunity to record an updated diagnosis and management plan. After discussing the AI diagnosis with the patient, a final management plan was agreed upon. Results Participants at both sites were high risk (for example, having a history of melanoma or being transplant recipients). 743 lesions were imaged in 214 participants. In total, 28 dermatology trainees and 17 consultant dermatologists provided diagnoses and management decisions, and 3 experienced teledermatologists provided remote assessments. A dedicated research nurse was essential to oversee study processes, maintain study documents, and assist with clinical workflow. In cases where AI algorithm and consultant dermatologist diagnoses were discordant, participant anxiety was an important factor in the final agreed management plan to biopsy or not. Conclusions Although AI algorithms are likely to be of most use in the primary care setting, higher event rates in specialist settings are important for the initial assessment of algorithm safety and accuracy. This study highlighted the importance of considering workflow issues and doctor-patient-AI interactions prior to larger-scale trials in community-based practices. Acknowledgments This research was supported by the Victorian Medical Research Acceleration Fund, with 1:1 contribution from MoleMap Ltd. VM is supported by the National Health and Medical Research Council Early Career Fellowship. CF is supported by the Monash University Research Training Program Scholarship. Conflicts of Interest SM is head of clinical research and regulatory affairs at Kahu.ai Ltd, a subsidiary of MoleMap Ltd. MH was the chief medical officer and a director of MoleMap Ltd, and holds shares in MoleMap Ltd. Trial Registration ClinicalTrials.gov NCT04040114; https://clinicaltrials.gov/ct2/show/NCT04040114

Lentigo maligna (LM) is a common subtype of in situ melanoma on chronically sun-exposed skin, particularly the head and neck of older patients. Although surgery is the standard treatment, there is associated morbidity, and options such as imiquimod cream or radiotherapy may be used if surgery is refused or inappropriate. Complete response rates following imiquimod treatment are variable in the literature. The aim of this study was to evaluate the host immune response both before and following treatment with imiquimod to better identify likely responders. Paired pre- and post-imiquimod treatment specimens were available for 27 patients. Patients were treated with imiquimod 5 days per week for 12 weeks; at 16 weeks, lesions were excised for histological assessment. Of the 27 patients, 16 were responders and 11 failed to clear the disease. PDL1 protein expression was increased, accompanied by a unique gene signature in lesions from patients that subsequently histologically cleared LM by 16 weeks. This comprised 57 upregulated immune genes in signaling networks for antigen presentation, type I interferon signaling, and T-cell activation. This may represent an early responder group to imiquimod, and this unique gene signature potentially can be used as a biomarker of LM response to imiquimod.

AIM: The American Society of Clinical Oncology and US Institute of Medicine emphasize the need to trial novel models of posttreatment care, and disseminate findings. In 2011, the Victorian State Government (Australia) established the Victorian Cancer Survivorship Program (VCSP), funding six 2-year demonstration projects, targeting end of initial cancer treatment. Projects considered various models, enrolling people of differing cancer types, age and residential areas. We sought to determine common enablers of success, as well as challenges/barriers. METHODS: Throughout the duration of the projects, a formal "community of practice" met regularly to share experiences. Projects provided regular formal progress reports. An analysis framework was developed to synthesize key themes and identify critical enablers and challenges. Two external reviewers examined final project reports. Discussion with project teams clarified content. RESULTS: Survivors reported interventions to be acceptable, appropriate and effective. Strong clinical leadership was identified as a critical success factor. Workforce education was recognized as important. Partnerships with consumers, primary care and community organizations; risk stratified pathways with rapid re-access to specialist care; and early preparation for survivorship, self-management and shared care models supported positive project outcomes. Tailoring care to individual needs and predicted risks was supported. Challenges included: lack of valid assessment and prediction tools; limited evidence to support novel care models; workforce redesign; and effective engagement with community-based care and issues around survivorship terminology. CONCLUSION: The VCSP project outcomes have added to growing evidence around posttreatment care. Future projects should consider the identified enablers and challenges when designing and implementing survivorship care.

Background Intraepidermal carcinoma (IEC), superficial basal cell carcinoma (sBCC), and psoriasis are common entities that may all present as well-defined, brightly erythematous plaques. Currently, there are limited data on the dermatoscopic features that differentiate these diagnoses. Objective We sought to describe the most significant morphologic findings seen on dermatoscopy of IEC, sBCC, and psoriasis, and formulate a diagnostic model based on these features. Method We conducted a retrospective observational study using macrophotography and dermatoscopy to evaluate the presence or absence of dermatoscopic features and formulated diagnostic models for each diagnosis. A convenient sample of 300 lesions was collected from 255 patients from two hospital dermatology clinics and 4 private dermatology practices. These comprised 150 cases of sBCC, 100 cases of psoriasis, and 50 cases of IEC. Results The most significant dermatoscopic features of IEC were a clustered vascular pattern, glomerular vessels, and hyperkeratosis. When all 3 features were observed together, the diagnostic probability for IEC was 98%. sBCCs were characterized by a scattered vascular pattern, arborizing microvessels, telangiectatic or atypical vessels, milky-pink background, and brown dots/globules; the diagnostic probability was 99% if 4 of these 6 features were identified. For psoriasis, the significant features identified were a homogenous vascular pattern, red dots, and light-red background, yielding a diagnostic probability of 99% if all 3 features were present. Limitations Lack of evaluation of interobserver/intraobserver reproducibility is a limitation. Conclusion Dermatoscopy is valuable in the diagnosis and differentiation of IEC, sBCC, and psoriasis because of consistent dermatoscopic morphology.

The American Society of Clinical Oncology and US Institute of Medicine emphasize the need to trial novel models of posttreatment care, and disseminate findings. In 2011, the Victorian State Government (Australia) established the Victorian Cancer Survivorship Program (VCSP), funding six 2-year demonstration projects, targeting end of initial cancer treatment. Projects considered various models, enrolling people of differing cancer types, age and residential areas. We sought to determine common enablers of success, as well as challenges/barriers.Throughout the duration of the projects, a formal "community of practice" met regularly to share experiences. Projects provided regular formal progress reports. An analysis framework was developed to synthesize key themes and identify critical enablers and challenges. Two external reviewers examined final project reports. Discussion with project teams clarified content.Survivors reported interventions to be acceptable, appropriate and effective. Strong clinical leadership was identified as a critical success factor. Workforce education was recognized as important. Partnerships with consumers, primary care and community organizations; risk stratified pathways with rapid re-access to specialist care; and early preparation for survivorship, self-management and shared care models supported positive project outcomes. Tailoring care to individual needs and predicted risks was supported. Challenges included: lack of valid assessment and prediction tools; limited evidence to support novel care models; workforce redesign; and effective engagement with community-based care and issues around survivorship terminology.The VCSP project outcomes have added to growing evidence around posttreatment care. Future projects should consider the identified enablers and challenges when designing and implementing survivorship care.

Merkel cell carcinoma (MCC) is an aggressive cutaneous malignancy with a high mortality rate. Diagnosis is often delayed.To characterize the dermoscopic features of MCC.Clinical and dermoscopic images of 12 biopsy-proven MCCs were analysed in a retrospective manner, with existing dermoscopic criteria being scored independently by three dermatologists.The four most frequent clinical features were cherry red colour, shiny surface, sharp circumscription and nodular morphology. Significant dermoscopic features included linear irregular and polymorphous vessels, poorly focused vessels, milky pink areas, white areas, structureless areas and architectural disorder. Pigmented structures were absent from all lesions.The dermoscopic features described herein help the clinician to distinguish MCC from other benign and malignant red nodules. Increasing recognition of the presenting features will facilitate earlier diagnosis of MCC and reduced mortality.

Objective To determine the efficacy of imiquimod cream, 5%, in the treatment of lentigo maligna (LM). Design Open-label before-and-after interventional study. Setting A multidisciplinary melanoma clinic at a major tertiary hospital. Patients Forty-three patients with biopsy-proven LM of greater than 5 mm in diameter completed this study. Interventions Imiquimod cream, 5%, was applied to the lesion 5 days a week for 12 weeks. The original lesion was excised with a 5-mm margin. Main Outcome Measures The primary outcome was histopathologic evidence of LM in the excision specimen assessed independently by 2 of 3 dermatopathologists. Visible inflammation during treatment and macroscopic clearance were recorded. Results When 5 of the 43 patients with discordant histopathologic assessment of the excision specimen were excluded, 20 of 38 patients (53% [95% confidence interval, 36%-69%]) demonstrated histopathologic clearance of LM after imiquimod treatment. Visible inflammation was significantly associated with histopathologic clearance (P = .04), but the positive predictive value was low (62%). Macroscopic clearance showed some association with histopathologic clearance (P = .11). Dermatopathologist concordance for all 43 specimens was substantial ( κ = 0.77; 95% confidence interval, 0.57-0.96). Conclusions Imiquimod cream, 5%, has limited efficacy in the treatment of LM when determined by histopathologic assessment of the entire treated area. The clinical signs of visible inflammation during treatment and apparent lesion clearance cannot be relied on to assess efficacy. Trial Registration anzctr.org.au Identifier: ACTRN12610000066088

SUMMARY A case of loose anagen syndrome presenting in an 8 year old girl as a 3 year history of unruly, slowly growing hair is dicussed.

• Zinc deficiency that was diagnosed at 14 weeks of age developed in a breast-fed premature infant. There was a rapid response to zinc supplements (20 mg/day) and therapy was stopped after three weeks without recurrent disease. The maternal breast milk had a low level of zinc and this could not be corrected by oral zinc supplements. ( Arch Dermatol 1983;119:319-321)